On July 30, we launched SKI (Voice coding for your agents) on Product Hunt, and by the end of the day it became the #1 Product of the Day. It was a moment we had dreamed about for months, and seeing all the hard work finally pay off is something we'll never forget. To everyone who upvoted, left a comment, reported a bug, shared feedback, or simply gave SKI a try, thank you. Every bit of support meant more than you know.
The launch introduced SKI to thousands of people, brought invaluable feedback, improved our visibility across search engines and AI search, and opened doors to opportunities we wouldn't have had otherwise. Beyond the numbers, it reminded us that great products aren't built in isolation. They're shaped by the people who use them.
As we continue building at Pattern AI Labs, we want this community to grow alongside us. That's why we've started a Discord community where we'll share early previews, product updates, behind-the-scenes progress, and new launches. More than that, it's a place for founders, developers, and anyone curious about the future of AI to connect, collaborate, share what they're building, learn from one another, and help shape what we build next.
In windows, it just overlays on top. I’d rather be able to hide it when I don’t need it. Notch seems like a good solution. Is there anything similar available for Windows?
SKI
@gigi_kuriakose Yes, there is a hide function for SKI, accessible via Preferences -> Hotkeys. Pill is currently the only option in Windows. Notch is limited to Mac.
@johnkg003 Supported! 🚀 Congrats on the launch and wishing you all the best. Hope you finish at #1! 🔥
SKI
@gigi_kuriakose Thanks a lot for your support. Please try out the product and let us know your feedback as well!
SKI
@johnkg003 @gigi_kuriakose 🔥
SKI
@gigi_kuriakose Thanks for trying SKI
SKI
@gigi_kuriakose Thanks again for checking SKI
SKI
@gigi_kuriakose 🔥
Voice coding makes total sense for describing intent, but a lot of my actual prompts to Claude Code are things like 'move the logic from RecurringContent.tsx into a new useRecurring hook in hooks/recurring' where exact file paths and camelCase names matter and saying them out loud is clunky. Does SKI do anything smart with recognizing code identifiers and paths specifically, or is that where the review-before-send step earns its keep?
SKI
@cannetjam Thanks a lot for taking a look at SKI.
Claude Code can understand correctly if you write "Recurring contents file" into a new "use Recurring" hook. LLMs are intelligent enough to understand file names, function names etc. It doesn't need any special change from SKI. We have tried it with Claude Code and it always works as they are very big models. They don't need us to have proper formatted names for it to recognize. They are very good at this.
Please try it out. You will be surprised by how good the LLMs are. Please let us know your feedback as well!
SKI
@cannetjam Thanks for trying SKI
SKI
@cannetjam 🔥
Does it have built in intelligence to understand and respond ? Or is it working like bring your own agent where the speech understood and spoken by Claude Code or our agents ?
SKI
@jaison1993 Thank you for asking. It doesn't have built-in LLM. It connects your voice with Claude Code or agents like Hermes. It also connects meetings to these agents. The intelligence comes from the agents connected.
@johnkg003 Are the meeting summaries generated by the connected agents ? Or do you send it to cloud like other platforms ?
SKI
@jaison1993 Yes, the summaries of the meetings and recordings are generated by the agents you connect to SKI. SKI doesn't have built in intelligence to summarize. So, your data is shared with your agent (could be a local LLM or a cloud LLM that you have subscribed to). You decide where to send the data to. We don't send your data to cloud.
SKI
@johnkg003 @jaison1993 Yes
SKI
@jaison1993 Thanks for sharing feedback
Congrats on the launch! Voice input for coding agents makes sense in a way it never did for typing code, since you're dictating intent rather than syntax. Curious how you handle the context switch when you need to reference a specific file or function mid-sentence. Is there a way to point at things while talking?
SKI
@lucasjpols Thanks a lot for checking out SKI. It makes a lot of sense now as we are dictating the intent. If the function names are simple and uses common words, it gets transcribed easily as part of the sentence and the LLM which receives it can make a lot of sense about the function from the transcribed words. For instance, if the function name is "function_mic" and the transcription gets it as "function mike", the LLM is intelligent enough to correctly identify the function. One addition would be to just tell the agent what the function does so that it can easily pick it up even in case of transcription errors.
You could also open the file up and ask the agent to take a look. Agent can take a screenshot, see the function code, and work on it.
SKI
@lucasjpols Thanks for trying SKI
SKI
@lucasjpols 🔥
Swytchcode
This is interesting. How do you highlight a specific code in a file using dictation? Just curious :)
SKI
@chilarai Multiple options
1. You could just say file name and the lines and LLMs now are intelligent enough to understand it.
2. You could open up the screen and just ask it to take a look at your screen - it can take screenshots and understand the lines. Or you could send screens using hotkeys along with your voice.
3. You could also talk just about the functionality implemented in the code and LLMs can understand them easily.
LLMs are now intelligent enough to understand and correct mistakes in transcription as well.
SKI
@chilarai Thanks again for checking SKI
SKI
@chilarai Thanks again for checking SKI
Would it be possible to share meeting transcripts with Claude Code for analysis and technical assistance?
SKI
@lakshmi_ravi Thank you for taking a look into our product. Yes, the meeting transcripts are stored as files in the selected project folder. Claude code or any other coding agent that you use can access and process it.
@johnkg003 Supported🎉 Wishing you an incredible launch day and congratulations in advance for #1🚀
SKI
@lakshmi_ravi Thanks a lot! Please try it out and let us know your feedback!
SKI
@johnkg003 @lakshmi_ravi Thanks
SKI
@lakshmi_ravi Thanks again for checking SKI
Congrats on the launch! Voice input for coding agents feels overdue. Does it handle multi step commands, or is it mostly one shot prompts right now?
SKI
@ben_kahan Thanks a lot for checking out SKI. It just works like a text input to the agent. So, it can handle multi step commands. Once the task is complete, it can respond back to you via voice.
SKI
@ben_kahan Thanks